© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 97029
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    iture
    -0.25
    alc
    -0.25
     swell
    -0.24
    iny
    -0.24
    è
    -0.24
    æĻ®éģįåŃĺåľ¨
    -0.24
    åĽŀäºĭ
    -0.24
    æ±ĩéĽĨ
    -0.24
    å¾Īéĩįè¦ģçļĦ
    -0.24
    æ¶Īæģ¯
    -0.24
    POSITIVE LOGITS
    åĮ¹
    0.30
    nants
    0.27
    '](
    0.26
    appendTo
    0.25
    avia
    0.25
     refreshed
    0.25
    "](
    0.25
    ợ
    0.24
    æķĮ
    0.24
    plate
    0.24
    Activations Density 0.784%

    No Known Activations